AI-Driven Recommendations for Strategic Urban Renewal

This paper presents a novel approach to urban renewal planning through a decision support system that integrates advanced algorithms and machine learning techniques. The system allows municipal stakeholders to explore new parcel combinations for renewal, going beyond the constraints of the existing urban layout. This unique approach, combined with a modular plugin architecture of the system, offers flexibility and transparency in the decision-making process. The plugins consist of custom-designed algorithmic solutions that address the specific and nuanced requirements of the field. Additionally, deep learning techniques are employed to predict the potential of future projects based on historical data. Identifying areas with the greatest potential for redevelopment is particularly crucial in peripheral regions, where profit margins are typically low. However, successful renewal in these areas can serve as a catalyst, fostering additional growth and development where it is most needed. Thus, the proposed model offers an effective solution to this challenge and has the potential to enhance urban renewal initiatives.